At CES 2025 in Las Vegas, NVIDIA unveiled its next-generation Rubin platform, marking a significant leap in AI computing. This new architecture comprises six specialized chips—including the Vera CPU, Rubin GPU, and ConnectX-9 SuperNIC—engineered to power the next wave of AI supercomputers. The platform is specifically designed to accelerate complex workloads like agentic AI, mixture-of-experts models, and long-context reasoning.

The announcement highlights how the existing DGX SuperPOD infrastructure remains the foundational design for deploying these future Rubin-based systems. By offering a full-stack solution that integrates computing, networking, and software, NVIDIA aims to remove the complexities of infrastructure integration for enterprises. This strategic move addresses the surging demand for both AI training and inference capabilities, allowing businesses to focus on innovation rather than hardware management.